Home / Current Issue / Paper 1706290
Comparison of K-Means and HDBSCAN Clustering Approaches to Enhance Marketing Strategies
Subject area: Science,Engineering and Technology · Area of research: Machine Learning
Abstract
Maintaining and growing market share is non-negotiable for businesses regardless of economic swings and the instability of many sectors. Many companies set aside large funds for marketing and advertising their goods and services meant to support their corporate objectives. But a Proxima (2023) analysis indicates that 60% of this spending may be better used, primarily because of poor targeting of the appropriate audience depending on their capacity and purchase patterns. Personalising marketing and sales communication and targeting will help one to maximise client satisfaction and optimise return on investment. This work investigates the application of machine learning models to examine a real-world dataset of 3,900 distinct consumers who regularly buy accessories, outerwear, shoes, and clothes. Customer clusters were segmented and understood using the Recency, Frequency, and Monetary (RFM) Model, K-Means and Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN) methods. High, medium, and low-paying clients were found by means of RFM scores. The results resulted in the creation of focused marketing plans emphasising on the 7Ps (Product, Place, Price, Promotion, People, Process, and Physical Evidence), therefore creating business prospects for favourable changes in several client categories. A reusable Python tool was also developed to examine big databases going forward.
Keywords
Customer Segmentation, HDBSCAN Clustering, KMeans Clustering, and The Recency Frequency Monetary Model.
How to cite this paper
@article{1706290,
author = {Raphael Ibraimoh, Adetunji Aderoba},
title = {Comparison of K-Means and HDBSCAN Clustering Approaches to Enhance Marketing Strategies},
journal = {Iconic Research And Engineering Journals},
year = {2024},
volume = {8},
number = {3},
pages = {272-282},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1706290.pdf},
abstract = {Maintaining and growing market share is non-negotiable for businesses regardless of economic swings and the instability of many sectors. Many companies set aside large funds for marketing and advertising their goods and services meant to support their corporate objectives. But a Proxima (2023) analysis indicates that 60% of this spending may be better used, primarily because of poor targeting of the appropriate audience depending on their capacity and purchase patterns. Personalising marketing and sales communication and targeting will help one to maximise client satisfaction and optimise return on investment. This work investigates the application of machine learning models to examine a real-world dataset of 3,900 distinct consumers who regularly buy accessories, outerwear, shoes, and clothes. Customer clusters were segmented and understood using the Recency, Frequency, and Monetary (RFM) Model, K-Means and Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN) methods. High, medium, and low-paying clients were found by means of RFM scores. The results resulted in the creation of focused marketing plans emphasising on the 7Ps (Product, Place, Price, Promotion, People, Process, and Physical Evidence), therefore creating business prospects for favourable changes in several client categories. A reusable Python tool was also developed to examine big databases going forward.},
keywords = {Customer Segmentation, HDBSCAN Clustering, KMeans Clustering, and The Recency Frequency Monetary Model.},
month = {September},
}